{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T15:58:48Z","timestamp":1787932728819,"version":"build-2784847793"},"reference-count":103,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T00:00:00Z","timestamp":1762992000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T00:00:00Z","timestamp":1762992000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Br J Haematol"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>Risk stratification is the backbone of clinical decision\u2010making for patients with haematological malignancies. Models currently used in routine clinical practice often rely on static rules, conventional statistics and expert consensus. While pragmatic and accessible, these models fail to capture the complex biological interactions and patient heterogeneity, especially as data dimensionality grows given the availability of more comprehensive molecular analysis. Artificial intelligence (AI), particularly machine learning (ML), offers the potential to process such high\u2010dimensional data, uncover latent patterns and provide dynamic, individualized risk predictions. In this review, we introduce haematologists to core concepts and limitations of AI\u2010based risk stratification. We examine studies in myeloid and lymphoid neoplasms developing AI models that challenge current standard models and identify novel disease subtypes and risk markers. While these models offer unique potential for data\u2010driven personalized decision support, several challenges remain to routine applicability such as training cohort composition, validation and bias mitigation highlighting an urgent need for interdisciplinary collaboration and dialogue with regulatory agencies to ensure robust and safe model deployment. As data dimensionality, digital infrastructure and regulatory frameworks evolve, AI\u2010guided risk stratification is poised to complement and potentially reshape clinical practice in malignant haematology requiring haematologists to be aware of potential capabilities and pitfalls.<\/jats:p>","DOI":"10.1111\/bjh.70231","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T08:51:42Z","timestamp":1763023902000},"page":"25-38","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Artificial intelligence for risk assessment and outcome prediction in malignant haematology"],"prefix":"10.1111","volume":"208","author":[{"given":"Jan\u2010Niklas","family":"Eckardt","sequence":"first","affiliation":[{"name":"Department of Internal Medicine I, University Hospital Carl Gustav Carus TUD Dresden University of Technology  Dresden Germany"},{"name":"Else Kr\u00f6ner Fresenius Center for Digital Health TUD Dresden University of Technology  Dresden Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wencke","family":"Walter","sequence":"additional","affiliation":[{"name":"MLL Munich Leukemia Laboratory  Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan Moritz","family":"Middeke","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine I, University Hospital Carl Gustav Carus TUD Dresden University of Technology  Dresden Germany"},{"name":"Else Kr\u00f6ner Fresenius Center for Digital Health TUD Dresden University of Technology  Dresden Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Torsten","family":"Haferlach","sequence":"additional","affiliation":[{"name":"MLL Munich Leukemia Laboratory  Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,11,13]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1182\/blood.2022016867"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1182\/blood-2012-03-420489"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199309303291402"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/10.508551"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0009-8981(03)00186-4"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-8652(199810)59:2<143::AID-AJH7>3.0.CO;2-Y"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1101\/gr.104003"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0300-7"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0307-0"},{"key":"e_1_2_11_11_1","unstructured":"MezzaliraE D'AgnoloM BoaroMP ReggianiG CelliniA BoaroA et\u00a0al.European Hematology Association 2025 Congress. [cited 2025 Aug 20]. Assessing Knowledge Gaps and Attitudes Towards Artificial Intelligence Among Healthcare Professionals Working in Haematology. Available from:https:\/\/library.ehaweb.org\/eha\/2025\/eha2025\u2010congress\/4162910\/elisabetta.mezzalira.assessing.knowledge.gaps.and.attitudes.towards.artificiai.html?f=menu%3D6%2Abrowseby%3D8%2Asortby%3D2%2Amedia%3D3%2Ace_id%3D2882%2Aot_id%3D31588%2Amarker%3D5845%2Afeatured%3D19595"},{"key":"e_1_2_11_12_1","volume-title":"Artificial intelligence, global edition","author":"Russell S","year":"2021"},{"key":"e_1_2_11_13_1","volume-title":"Deep learning","author":"Goodfellow IJ","year":"2016"},{"key":"e_1_2_11_14_1","first-page":"1097","volume-title":"NIPS'12: Proceedings of the 26th International Conference on Neural Information Processing Systems \u2013 Volume 1","author":"Krizhevsky A","year":"2012"},{"key":"e_1_2_11_15_1","unstructured":"VaswaniA ShazeerN ParmarN UszkoreitJ JonesL GomezAN et\u00a0al.Attention is all you need.2017arXiv.org. [cited 2025 Apr 23]. Available from:https:\/\/arxiv.org\/abs\/1706.03762v7"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13184624"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106854"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03583-3"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.12126"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-019-1466-7"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2"},{"key":"e_1_2_11_22_1","unstructured":"GuoC PleissG SunY WeinbergerKQ.On calibration of modern neural networks [Internet]. arXiv2017[cited 2025 Oct 8]. Available from:http:\/\/arxiv.org\/abs\/1706.04599"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09975-1"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.leukres.2021.106639"},{"issue":"9","key":"e_1_2_11_25_1","first-page":"2435","article-title":"Artificial intelligence to empower diagnosis of myelodysplastic syndromes by multiparametric flow cytometry","volume":"108","author":"Clichet V","year":"2023","journal-title":"Haematologica"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.20.02810"},{"issue":"10","key":"e_1_2_11_27_1","article-title":"Machine learning improves risk stratification in myelodysplastic neoplasms: an analysis of the Spanish Group of Myelodysplastic Syndromes","volume":"7","author":"Mosquera Orgueira A","year":"2023","journal-title":"Hema"},{"key":"e_1_2_11_28_1","article-title":"Genomic biomarkers to predict resistance to hypomethylating agents in patients with myelodysplastic syndromes using artificial intelligence","volume":"3","author":"Nazha A","year":"2019","journal-title":"JCO Precis Oncol"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2022.104931"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15164019"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-022-01980-w"},{"issue":"1","key":"e_1_2_11_32_1","article-title":"Machine learning improves risk stratification in myelofibrosis: an analysis of the Spanish registry of myelofibrosis","volume":"7","author":"Mosquera\u2010Orgueira A","year":"2023","journal-title":"Hema"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41375-022-01773-0"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1182\/blood.2024027287"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1080\/10428194.2020.1798951"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41408-019-0244-2"},{"issue":"5","key":"e_1_2_11_37_1","article-title":"Age\u2010stratified machine learning identifies divergent prognostic significance of molecular alterations in AML","volume":"9","author":"Eckardt JN","year":"2025","journal-title":"Hema"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.3324\/haematol.2021.280027"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-023-00298-6"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.1177\/1176935119835544"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1182\/bloodadvances.2018030726"},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0254976"},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2025.e42030"},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1038\/35000501"},{"key":"e_1_2_11_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/nm0102-68"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0016-8"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1801445"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12094-023-03326-y"},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12672-025-02349-x"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.18.00025"},{"key":"e_1_2_11_51_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-020-07492-y"},{"key":"e_1_2_11_52_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0311261"},{"key":"e_1_2_11_53_1","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.650"},{"key":"e_1_2_11_54_1","doi-asserted-by":"publisher","DOI":"10.1093\/bfgp\/elac038"},{"key":"e_1_2_11_55_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40364-024-00716-4"},{"key":"e_1_2_11_56_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph18052679"},{"key":"e_1_2_11_57_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.705010\/full"},{"key":"e_1_2_11_58_1","doi-asserted-by":"publisher","DOI":"10.3390\/make2040035"},{"key":"e_1_2_11_59_1","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare10010155"},{"key":"e_1_2_11_60_1","doi-asserted-by":"publisher","DOI":"10.1158\/2767-9764.CRC-23-0083"},{"key":"e_1_2_11_61_1","doi-asserted-by":"publisher","DOI":"10.21037\/atm-22-5815"},{"key":"e_1_2_11_62_1","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.23.00255"},{"key":"e_1_2_11_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12094-015-1285-z"},{"key":"e_1_2_11_64_1","doi-asserted-by":"publisher","DOI":"10.1177\/1460458216655188"},{"issue":"1","key":"e_1_2_11_65_1","article-title":"On the challenges of predicting treatment response in Hodgkin's lymphoma using transcriptomic data","volume":"16","author":"Patr\u00edcio A","year":"2023","journal-title":"BMC Med Genet"},{"key":"e_1_2_11_66_1","doi-asserted-by":"publisher","DOI":"10.2147\/IJGM.S341557"},{"key":"e_1_2_11_67_1","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.18.00137"},{"key":"e_1_2_11_68_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105490"},{"key":"e_1_2_11_69_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1198992\/full"},{"key":"e_1_2_11_70_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2019.00079\/full"},{"key":"e_1_2_11_71_1","doi-asserted-by":"publisher","DOI":"10.1182\/bloodadvances.2021006351"},{"key":"e_1_2_11_72_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-14225-8"},{"key":"e_1_2_11_73_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa060"},{"key":"e_1_2_11_74_1","doi-asserted-by":"publisher","DOI":"10.3390\/curroncol30020148"},{"key":"e_1_2_11_75_1","doi-asserted-by":"publisher","DOI":"10.1158\/1078-0432.CCR-21-3430"},{"key":"e_1_2_11_76_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01189-3"},{"key":"e_1_2_11_77_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.922039"},{"key":"e_1_2_11_78_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tranon.2021.101157"},{"key":"e_1_2_11_79_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41375-021-01286-2"},{"key":"e_1_2_11_80_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41408-022-00647-z"},{"key":"e_1_2_11_81_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0254596"},{"key":"e_1_2_11_82_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.652063"},{"key":"e_1_2_11_83_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijms242115570"},{"key":"e_1_2_11_84_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers16213709"},{"key":"e_1_2_11_85_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00323-1"},{"key":"e_1_2_11_86_1","unstructured":"Home \u2010 HARMONY Healthcare Alliance [Internet]. [cited 2025 June 16]. Available from:https:\/\/www.harmony\u2010alliance.eu\/"},{"key":"e_1_2_11_87_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01076-x"},{"key":"e_1_2_11_88_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(20)30186-2"},{"key":"e_1_2_11_89_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2021.100347"},{"key":"e_1_2_11_90_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-52618-6"},{"key":"e_1_2_11_91_1","doi-asserted-by":"publisher","DOI":"10.1038\/bjc.2014.639"},{"key":"e_1_2_11_92_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"e_1_2_11_93_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03425-5"},{"key":"e_1_2_11_94_1","volume-title":"Good machine learning practice for medical device development: guiding principles","author":"Food and Drug Administration","year":"2025"},{"key":"e_1_2_11_95_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0101-9"},{"key":"e_1_2_11_96_1","doi-asserted-by":"publisher","DOI":"10.1182\/blood.2020010568"},{"key":"e_1_2_11_97_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mpdhp.2025.03.002"},{"key":"e_1_2_11_98_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-023-02397-9"},{"key":"e_1_2_11_99_1","doi-asserted-by":"publisher","DOI":"10.1053\/j.semnuclmed.2025.02.007"},{"key":"e_1_2_11_100_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41375\u2010021\u201001408\u2010w"},{"key":"e_1_2_11_101_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-022-09307-8"},{"key":"e_1_2_11_102_1","doi-asserted-by":"publisher","DOI":"10.1002\/cyto.b.22166"},{"key":"e_1_2_11_103_1","doi-asserted-by":"publisher","DOI":"10.3390\/genes16060685"},{"key":"e_1_2_11_104_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41576-022-00532-2"}],"container-title":["British Journal of Haematology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/bjh.70231","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/bjh.70231","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/bjh.70231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T02:20:10Z","timestamp":1771035610000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/bjh.70231"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,13]]},"references-count":103,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1111\/bjh.70231"],"URL":"https:\/\/doi.org\/10.1111\/bjh.70231","archive":["Portico"],"relation":{},"ISSN":["0007-1048","1365-2141"],"issn-type":[{"value":"0007-1048","type":"print"},{"value":"1365-2141","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,13]]},"assertion":[{"value":"2025-08-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}